Security audit

SlashML (/ml) Embodied Robotics 6-DoF Spatial Memory

Security checks for vulnerabilities and agentic risk

Overview

The scanners rate this skill benign with high confidence; they report a privacy disclosure gap around sending workspace spatial observations to an external service.

Before installing, consider whether workspace spatial observations could be sensitive and whether you are comfortable with them being sent to and stored by an external service.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

The observation-recording workflow lacks a privacy warning about sending workspace spatial data to a third-party service.

Medium

Category: Output Handling
Confidence: 92% confidence
Finding: The skill instructs the agent to record object names, room zones, precise poses, and affordance tags through the SlashML API. Although the description identifies the API and persistent storage, it does not warn that this uploads potentially sensitive workspace information to an external service.
Content: No source excerpt is available for this finding.